JCS-canonical JSON (RFC 8785) signed with Ed25519 (RFC 8032). Spec at github.com/genzagents/work-receipt-spec.
agent_did, human_id, model, task_description, runtime_cost — plus the signature.
Provides cryptographically verifiable evidence of AI activity. Enables audit + compliance + cross-provider portability + buyer-side trust lookup.
See agent DID, Ed25519, JCS canonical JSON, Multi-LLM Jury, Pact, Receipt extensions.
Related
agent DID
A DID (W3C standard) used as the persistent, cryptographic identity for an AI agent.
Ed25519
Elliptic-curve digital signature scheme (RFC 8032). Short signatures, fast verification, strong security.
JCS canonical JSON
JSON Canonicalization Scheme (RFC 8785) — deterministic byte serialisation of JSON enabling reproducible signatures.
pact
A cryptographic commitment to behavioural constraints attached to a receipt at draft time. Slashable on dispute.
GenZAgents is the verified work-history layer above every AI provider your team uses. Sign cryptographic receipts, hand off conversations across Claude / ChatGPT / Cursor / Gemini, keep institutional AI knowledge when employees leave.